MathAcademy really is fantastic. I've done 5300 xp so far (80+ hours), and am almost finished with their Math for Machine Learning. It's remediated a lot of things I've struggled with during my University ML classes. Seriously a wonderful pedagogical experience. I can integrate multivariate functions easily, know all my derivative trig identities, and I don't get confused by continuous random variables any more.
back
1 comments
I'm working through Foundations specifically to do Math for Machine Learning and I'm very excited for that course. What were your thoughts on it?
Also, if they ever did a Math for Computer Graphics course I'd never cancel my subscription.
I think Math for ML is __fantastic__. And based on the curriculum Jason has published for ML, it seems very __very__ promising. I've done a fair bit of ML @ Cornell, so I've had exposure to a lot of the material he plans on covering. However, I glossed over a lot of the theory because some weakness in my math. I feel like this has been remediated with M4ML and ML should expand and solidify my understanding.
Edit: Wrt to computer graphics, going through M4ML and the ML sequence will really help you understand what's happening there. Convolutional Neural Nets, Gaussian Splatting, all rely on these same principles.
Is there another ML course besides Math for ML? If so can you share a link
I just started going through Math for ML and can also attest, it is amazing. Pedagogically revolutionary, and helping me fix up all sorts of gaps in my math background.
they do. in a ways, 90% of computer graphics is linear algebra and multivariate calculus. both are subjects you will find in mathacademy. once you learn those two, I recommend Peter shirley's book for a lesson on how to apply what you learned to computer graphics. https://www.amazon.com/Fundamentals-Computer-Graphics-Steve-...
It’s just ok. Certainly better than watching some random yt videos or passively reading a tb. For context I did ~11k pts to finish M4ML. It’s a little frustrating to see them chase the money and make ML/programming courses while the core differentiator (lesson quality) is still lacking in the later math topics. There are persistent issues that annoyed me so much that by the end it was like pulling teeth go grind out the points every day.
It has you overfit on the style of questions they ask, and I never felt like I got a good grasp of lots of the later topics despite passing my reviews and quizzes no problem.
Can you go into more detail about your experience it’s difficult to find negative or critical reviews of MathAcademy. (Well except reviews in the same vein as Paul Lockhart’s A Mathematician’s Lament [1])
I’m taking their Math Foundations 2 now. So far my only two complaints are:
1. Everything feels like a random grab bag of “tricks”. There isn’t a coherent presentation of why this works or why it’s important. 2. Geometry lessons just suck. I don’t blame MathAcademy for this, since they basically follow what would be considered standard American high school geometry curriculum. But after having gone through Euclid’s Elements, everything here just feels empty by comparison.
Overall I’m still very happy with the product. They do largely deliver on their promises.
https://worrydream.com/refs/Lockhart_2002_-_A_Mathematician'...
I know this is extremely pedantic, but I think you mean in the same "vein" instead of "vain".
Updated. Thanks.